ganarajpr/awesome-dspy

An Awesome list of curated DSPy resources.

What it solves

This project is a curated directory of resources about DSPy, a library that turns ordinary language model calls into self-improving pipelines. It solves the problem of finding quality tools, examples, and learning material when you want to build with DSPy but don't know where to start.

How it works

The repository is an Awesome list — a hand-picked collection of links organized by category. It lists projects that build on DSPy (like code review tools, agents, RAG examples), blog posts and tutorials, Twitter threads, a newsletter, videos, and academic papers. Each entry is a short description with a link to the external resource. There is no code or installation; the list itself is the content.

Who it's for

Developers, researchers, and teams who are using or considering DSPy for building language model applications. It's for anyone who wants to explore what's possible with DSPy, see concrete examples, watch explanatory videos, or read articles about best practices and production use.

Highlights

  • Dozens of community projects — from automated code review (CodeSpy) to voice AI testing (voicetest) to crypto payment adapters (AlgoVoi).
  • Hands-on tutorials and videos — including a full book on building LLM applications with DSPy and a step-by-step video playlist covering signatures, modules, and optimizers.
  • Production insights — articles about monitoring, tracing, and deploying DSPy in real systems.
  • Academic papers — links to foundational DSPy papers like DSPy Assertions for self-refining pipelines.
  • Regularly updated — resources like the DSPyWeekly newsletter keep the community informed.

Related

  • Project
    nick7nlp/Awesome-LLM-On-Policy-Distillation

    A curated reading companion that organizes 362 papers on on-policy distillation for large language models, with concise summaries, code links, thematic groupings, and guided reading paths — helping researchers navigate this fast-moving subfield.

  • Project
    fudan-generative-vision/Remory

    Remory is a plug‑in that adds a learned “residual memory” to large language models, enabling them to compact long conversation histories while preserving important information. It works with frozen base models (Qwen 3.8‑27B or GLM‑5.3‑Flash) and provides a SGLang server, a Codex UI integration, and a Python API for summarising, encoding residual memory, and continuing generation from a compacted checkpoint.

  • Project
    changwookjun/nlp-paper

    A curated list of natural language processing research papers, organized into categories from BERT and Transformers to large language models and retrieval-augmented generation. It helps researchers quickly find seminal and recent works in specific NLP areas.

  • Project
    SillyTavern/SillyTavern-Launcher

    A centralized launcher and installer for SillyTavern and various AI text, image, and voice generation platforms, simplifying local AI setup and management.